clicky-repo-operator
Pass
Audited by Gen Agent Trust Hub on Jun 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill contains no malicious code, obfuscated content, or hardcoded credentials. It serves a clear, documented purpose for repository operations.
- [COMMAND_EXECUTION]: The skill instructs the agent to use local git, gh, and terminal commands to manage branches, commits, and tests. These capabilities are appropriate for the skill's purpose and are mitigated by instructions to confirm actions with the user.
- [EXTERNAL_DOWNLOADS]: The skill performs repository cloning and interacts with remote GitHub infrastructure as a primary function, which is done only after resolving and confirming the target repository.
- [PROMPT_INJECTION]: The skill exhibits an Indirect Prompt Injection surface. 1. Ingestion points: External software repositories and GitHub PR/Issue data (SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: git, gh, and terminal command execution (SKILL.md). 4. Sanitization: Absent. While the surface exists, the instructions do not attempt to override safety protocols or bypass agent constraints.
Audit Metadata